© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 86960
    Prev
    Next
    INDEX
    Explanations

    citation markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gemeenten
    -1.47
     शुर
    -1.32
    方がいい
    -1.30
    ほうがいい
    -1.30
     ujar
    -1.23
    
    -1.20
     extraordinary
    -1.17
    ⸒
    -1.17
     ilumin
    -1.16
     lavish
    -1.16
    POSITIVE LOGITS
    <bos>
    1.60
    ↵↵
    1.57
    そのため
    1.37
    ,.
    1.36
    なので
    1.36
     thus
    1.34
    もあって
    1.34
    )
    1.34
    や
    1.29
    があり
    1.26
    Activations Density 0.072%

    No Known Activations